feedzirra 0.1.2 → 0.1.3

data/lib/feedzirra/feed.rb

@@ -46,7 +46,7 @@ module Feedzirra
     # === Returns
     # A array of class names.
     def self.feed_classes
-      @feed_classes ||= [Feedzirra::Parser::RSSFeedBurner, Feedzirra::Parser::RSS, Feedzirra::Parser::AtomFeedBurner, Feedzirra::Parser::Atom]
+      @feed_classes ||= [Feedzirra::Parser::RSSFeedBurner, Feedzirra::Parser::RSS, Feedzirra::Parser::GoogleDocsAtom, Feedzirra::Parser::AtomFeedBurner, Feedzirra::Parser::Atom, Feedzirra::Parser::ITunesRSS]
     end
     
     # Makes all registered feeds types look for the passed in element to parse.
@@ -279,7 +279,7 @@ module Feedzirra
           
           if klass
             begin
-              feed = klass.parse(xml, Proc.new{|message| puts "Error while parsing [#{url}] #{message}" })
+              feed = klass.parse(xml, Proc.new{|message| warn "Error while parsing [#{url}] #{message}" })
               feed.feed_url = c.last_effective_url
               feed.etag = etag_from_header(c.header_str)
               feed.last_modified = last_modified_from_header(c.header_str)
@@ -332,7 +332,7 @@ module Feedzirra
         curl.on_success do |c|
           begin
             add_feed_to_multi(multi, feed_queue.shift, feed_queue, responses, options) unless feed_queue.empty?
-            updated_feed = Feed.parse(c.body_str){ |message| puts "Error while parsing [#{feed.feed_url}] #{message}" }
+            updated_feed = Feed.parse(c.body_str){ |message| warn "Error while parsing [#{feed.feed_url}] #{message}" }
             updated_feed.feed_url = c.last_effective_url
             updated_feed.etag = etag_from_header(c.header_str)
             updated_feed.last_modified = last_modified_from_header(c.header_str)
@@ -381,4 +381,4 @@ module Feedzirra
       Time.parse($1) if $1
     end
   end
-end
+end

data/lib/feedzirra/feed_entry_utilities.rb

@@ -11,7 +11,7 @@ module Feedzirra
       begin
         DateTime.parse(string).feed_utils_to_gm_time
       rescue
-        puts "DATE CAN'T BE PARSED: [#{string}]"
+        warn "Failed to parse date #{string.inspect}"
         nil
       end
     end

data/lib/feedzirra/feed_utilities.rb

@@ -50,23 +50,12 @@ module Feedzirra
     private
 
     def find_new_entries_for(feed)
-      # this implementation is a hack, which is why it's so ugly.
-      # it's to get around the fact that not all feeds have a published date.
-      # however, they're always ordered with the newest one first.
-      # So we go through the entries just parsed and insert each one as a new entry
-      # until we get to one that has the same url as the the newest for the feed
-      return feed.entries if self.entries.length == 0
-      latest_entry = self.entries.first
-      found_new_entries = []
-      feed.entries.each do |entry|
-        break if entry.url == latest_entry.url
-        found_new_entries << entry
-      end
-      found_new_entries
+      # this algorithm does not optimize based on publication date, but always finds new entries
+      feed.entries.reject {|entry| self.entries.any? {|e| e.url == entry.url} }
     end
 
     def existing_entry?(test_entry)
       entries.any? { |entry| entry.url == test_entry.url }
     end
   end
-end
+end

data/lib/feedzirra/parser/atom.rb

@@ -26,4 +26,4 @@ module Feedzirra
     end
   end
 
-end
+end

data/lib/feedzirra/parser/google_docs_atom.rb

@@ -0,0 +1,28 @@
+require File.expand_path('./atom', File.dirname(__FILE__))
+
+module Feedzirra
+  module Parser
+    class GoogleDocsAtom
+      include SAXMachine
+      include FeedUtilities
+      element :title
+      element :subtitle, :as => :description
+      element :link, :as => :url, :value => :href, :with => {:type => "text/html"}
+      element :link, :as => :feed_url, :value => :href, :with => {:type => "application/atom+xml"}
+      elements :link, :as => :links, :value => :href
+      elements :entry, :as => :entries, :class => GoogleDocsAtomEntry
+
+      def url
+        @url ||= links.first
+      end
+
+      def self.able_to_parse?(xml) #:nodoc:
+        %r{<id>https?://docs.google.com/.*\</id\>} =~ xml
+      end
+
+      def feed_url
+        @feed_url ||= links.first
+      end
+    end
+  end
+end

data/lib/feedzirra/parser/google_docs_atom_entry.rb

@@ -0,0 +1,29 @@
+module Feedzirra
+  module Parser
+    class GoogleDocsAtomEntry
+      include SAXMachine
+      include FeedEntryUtilities
+      
+      element :title
+      element :link, :as => :url, :value => :href, :with => {:type => "text/html", :rel => "alternate"}
+      element :name, :as => :author
+      element :content
+      element :summary
+      element :published
+      element :id, :as => :entry_id
+      element :created, :as => :published
+      element :issued, :as => :published
+      element :updated
+      element :modified, :as => :updated
+      elements :category, :as => :categories, :value => :term
+      elements :link, :as => :links, :value => :href
+      element :"docs:md5Checksum", :as => :checksum
+      element :"docs:filename", :as => :original_filename
+      element :"docs:suggestedFilename", :as => :suggested_filename
+
+      def url
+        @url ||= links.first
+      end
+    end
+  end
+end

data/lib/feedzirra/parser.rb

@@ -9,6 +9,9 @@ module Feedzirra
     autoload :ITunesRSSItem,  'feedzirra/parser/itunes_rss_item'
     autoload :ITunesRSSOwner, 'feedzirra/parser/itunes_rss_owner'
 
+    autoload :GoogleDocsAtom,      'feedzirra/parser/google_docs_atom'
+    autoload :GoogleDocsAtomEntry, 'feedzirra/parser/google_docs_atom_entry'
+
     autoload :Atom,                'feedzirra/parser/atom'
     autoload :AtomEntry,           'feedzirra/parser/atom_entry'
     autoload :AtomFeedBurner,      'feedzirra/parser/atom_feed_burner'

data/lib/feedzirra/version.rb

@@ -1,3 +1,3 @@
 module Feedzirra
-  VERSION = '0.1.2'
+  VERSION = '0.1.3'
 end

data/spec/feedzirra/feed_spec.rb

@@ -97,6 +97,10 @@ describe Feedzirra::Feed do
   end
 
   describe "#determine_feed_parser_for_xml" do
+    it 'should return the Feedzirra::Parser::GoogleDocsAtom calss for a Google Docs atom feed' do
+      Feedzirra::Feed.determine_feed_parser_for_xml(sample_google_docs_list_feed).should == Feedzirra::Parser::GoogleDocsAtom
+    end
+
     it "should return the Feedzirra::Parser::Atom class for an atom feed" do
       Feedzirra::Feed.determine_feed_parser_for_xml(sample_atom_feed).should == Feedzirra::Parser::Atom
     end
@@ -590,4 +594,4 @@ describe Feedzirra::Feed do
       it "should return an return an array of feed objects if multiple feeds are passed in" 
     end
   end
-end
+end

data/spec/feedzirra/parser/google_docs_atom_entry_spec.rb

@@ -0,0 +1,22 @@
+require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
+
+describe Feedzirra::Parser::GoogleDocsAtomEntry do
+  describe 'parsing' do
+    before do
+      @feed = Feedzirra::Parser::GoogleDocsAtom.parse(sample_google_docs_list_feed)
+      @entry = @feed.entries.first
+    end
+
+    it 'should have the custom checksum element' do
+      @entry.checksum.should eql '2b01142f7481c7b056c4b410d28f33cf'
+    end
+
+    it 'should have the custom filename element' do
+      @entry.original_filename.should eql "MyFile.pdf"
+    end
+
+    it 'should have the custom suggested filename element' do
+      @entry.suggested_filename.should eql "TaxDocument.pdf"
+    end
+  end
+end

data/spec/feedzirra/parser/google_docs_atom_spec.rb

@@ -0,0 +1,31 @@
+require File.join(File.dirname(__FILE__), %w[.. .. spec_helper])
+
+describe Feedzirra::Parser::GoogleDocsAtom do
+  describe '.able_to_parser?' do
+    it 'should return true for Google Docs feed' do
+      Feedzirra::Parser::GoogleDocsAtom.should be_able_to_parse(sample_google_docs_list_feed)
+    end
+
+    it 'should not be able to parse another Atom feed' do
+      Feedzirra::Parser::GoogleDocsAtom.should_not be_able_to_parse(sample_atom_feed)
+    end
+  end
+
+  describe 'parsing' do
+    before do
+      @feed = Feedzirra::Parser::GoogleDocsAtom.parse(sample_google_docs_list_feed)
+    end
+
+    it 'should return a bunch of objects' do
+      @feed.entries.should_not be_empty
+    end
+
+    it 'should populate a title, interhited from the Atom entry' do
+      @feed.title.should_not be_nil
+    end
+
+    it 'should return a bunch of entries of type GoogleDocsAtomEntry' do
+      @feed.entries.first.should be_a Feedzirra::Parser::GoogleDocsAtomEntry
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -64,6 +64,10 @@ end
 def sample_wfw_feed
   load_sample("PaulDixExplainsNothingWFW.xml")
 end       
+
+def sample_google_docs_list_feed
+  load_sample("GoogleDocsList.xml")
+end       
        
 # http://eigenclass.org/hiki/Changes+in+Ruby+1.9#l156
 # Default Time.to_s changed in 1.9, monkeypatching it back
@@ -71,4 +75,4 @@ class Time
   def to_s
     strftime("%a %b %d %H:%M:%S %Z %Y")
   end
-end
+end

metadata

@@ -1,181 +1,134 @@
---- !ruby/object:Gem::Specification 
+--- !ruby/object:Gem::Specification
 name: feedzirra
-version: !ruby/object:Gem::Version 
-  prerelease: false
-  segments: 
-  - 0
-  - 1
-  - 2
-  version: 0.1.2
+version: !ruby/object:Gem::Version
+  version: 0.1.3
+  prerelease: 
 platform: ruby
-authors: 
+authors:
 - Paul Dix
 - Julien Kirch
 autorequire: 
 bindir: bin
 cert_chain: []
-
-date: 2011-09-30 00:00:00 -04:00
-default_executable: 
-dependencies: 
-- !ruby/object:Gem::Dependency 
+date: 2011-09-30 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
   name: nokogiri
-  prerelease: false
-  requirement: &id001 !ruby/object:Gem::Requirement 
+  requirement: &70245154994900 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        segments: 
-        - 1
-        - 4
-        - 4
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
         version: 1.4.4
   type: :runtime
-  version_requirements: *id001
-- !ruby/object:Gem::Dependency 
-  name: sax-machine
   prerelease: false
-  requirement: &id002 !ruby/object:Gem::Requirement 
+  version_requirements: *70245154994900
+- !ruby/object:Gem::Dependency
+  name: sax-machine
+  requirement: &70245154994260 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
+    requirements:
     - - ~>
-      - !ruby/object:Gem::Version 
-        segments: 
-        - 0
-        - 1
-        - 0
+      - !ruby/object:Gem::Version
         version: 0.1.0
   type: :runtime
-  version_requirements: *id002
-- !ruby/object:Gem::Dependency 
-  name: curb
   prerelease: false
-  requirement: &id003 !ruby/object:Gem::Requirement 
+  version_requirements: *70245154994260
+- !ruby/object:Gem::Dependency
+  name: curb
+  requirement: &70245154993700 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
+    requirements:
     - - ~>
-      - !ruby/object:Gem::Version 
-        segments: 
-        - 0
-        - 7
-        - 15
+      - !ruby/object:Gem::Version
         version: 0.7.15
   type: :runtime
-  version_requirements: *id003
-- !ruby/object:Gem::Dependency 
-  name: builder
   prerelease: false
-  requirement: &id004 !ruby/object:Gem::Requirement 
+  version_requirements: *70245154993700
+- !ruby/object:Gem::Dependency
+  name: builder
+  requirement: &70245154993160 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        segments: 
-        - 2
-        - 1
-        - 2
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
         version: 2.1.2
   type: :runtime
-  version_requirements: *id004
-- !ruby/object:Gem::Dependency 
-  name: activesupport
   prerelease: false
-  requirement: &id005 !ruby/object:Gem::Requirement 
+  version_requirements: *70245154993160
+- !ruby/object:Gem::Dependency
+  name: activesupport
+  requirement: &70245154845640 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
+    requirements:
     - - ~>
-      - !ruby/object:Gem::Version 
-        segments: 
-        - 3
-        - 0
-        - 8
-        version: 3.0.8
+      - !ruby/object:Gem::Version
+        version: 3.1.1
   type: :runtime
-  version_requirements: *id005
-- !ruby/object:Gem::Dependency 
-  name: loofah
   prerelease: false
-  requirement: &id006 !ruby/object:Gem::Requirement 
+  version_requirements: *70245154845640
+- !ruby/object:Gem::Dependency
+  name: loofah
+  requirement: &70245154844980 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
+    requirements:
     - - ~>
-      - !ruby/object:Gem::Version 
-        segments: 
-        - 1
-        - 2
-        - 0
+      - !ruby/object:Gem::Version
         version: 1.2.0
   type: :runtime
-  version_requirements: *id006
-- !ruby/object:Gem::Dependency 
-  name: rdoc
   prerelease: false
-  requirement: &id007 !ruby/object:Gem::Requirement 
+  version_requirements: *70245154844980
+- !ruby/object:Gem::Dependency
+  name: rdoc
+  requirement: &70245154844420 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
+    requirements:
     - - ~>
-      - !ruby/object:Gem::Version 
-        segments: 
-        - 3
-        - 8
-        version: "3.8"
+      - !ruby/object:Gem::Version
+        version: '3.8'
   type: :runtime
-  version_requirements: *id007
-- !ruby/object:Gem::Dependency 
-  name: rake
   prerelease: false
-  requirement: &id008 !ruby/object:Gem::Requirement 
+  version_requirements: *70245154844420
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: &70245154843940 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        segments: 
-        - 0
-        - 8
-        - 7
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
         version: 0.8.7
   type: :runtime
-  version_requirements: *id008
-- !ruby/object:Gem::Dependency 
-  name: i18n
   prerelease: false
-  requirement: &id009 !ruby/object:Gem::Requirement 
+  version_requirements: *70245154843940
+- !ruby/object:Gem::Dependency
+  name: i18n
+  requirement: &70245154843440 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
-    - - ">="
-      - !ruby/object:Gem::Version 
-        segments: 
-        - 0
-        - 5
-        - 0
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
         version: 0.5.0
   type: :runtime
-  version_requirements: *id009
-- !ruby/object:Gem::Dependency 
-  name: rspec
   prerelease: false
-  requirement: &id010 !ruby/object:Gem::Requirement 
+  version_requirements: *70245154843440
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: &70245154842920 !ruby/object:Gem::Requirement
     none: false
-    requirements: 
+    requirements:
     - - ~>
-      - !ruby/object:Gem::Version 
-        segments: 
-        - 2
-        - 6
-        - 0
+      - !ruby/object:Gem::Version
         version: 2.6.0
   type: :development
-  version_requirements: *id010
-description: "A feed fetching and parsing library that treats the internet like Godzilla treats Japan: it dominates and eats all."
+  prerelease: false
+  version_requirements: *70245154842920
+description: ! 'A feed fetching and parsing library that treats the internet like
+  Godzilla treats Japan: it dominates and eats all.'
 email: feedzirra@googlegroups.com
 executables: []
-
 extensions: []
-
 extra_rdoc_files: []
-
-files: 
+files:
 - lib/feedzirra/core_ext/date.rb
 - lib/feedzirra/core_ext/string.rb
 - lib/feedzirra/core_ext.rb
@@ -186,6 +139,8 @@ files:
 - lib/feedzirra/parser/atom_entry.rb
 - lib/feedzirra/parser/atom_feed_burner.rb
 - lib/feedzirra/parser/atom_feed_burner_entry.rb
+- lib/feedzirra/parser/google_docs_atom.rb
+- lib/feedzirra/parser/google_docs_atom_entry.rb
 - lib/feedzirra/parser/itunes_rss.rb
 - lib/feedzirra/parser/itunes_rss_item.rb
 - lib/feedzirra/parser/itunes_rss_owner.rb
@@ -208,6 +163,8 @@ files:
 - spec/feedzirra/parser/atom_feed_burner_entry_spec.rb
 - spec/feedzirra/parser/atom_feed_burner_spec.rb
 - spec/feedzirra/parser/atom_spec.rb
+- spec/feedzirra/parser/google_docs_atom_entry_spec.rb
+- spec/feedzirra/parser/google_docs_atom_spec.rb
 - spec/feedzirra/parser/itunes_rss_item_spec.rb
 - spec/feedzirra/parser/itunes_rss_owner_spec.rb
 - spec/feedzirra/parser/itunes_rss_spec.rb
@@ -220,39 +177,31 @@ files:
 - README.rdoc
 - Rakefile
 - .rspec
-has_rdoc: true
 homepage: http://github.com/pauldix/feedzirra
 licenses: []
-
 post_install_message: 
 rdoc_options: []
-
-require_paths: 
+require_paths:
 - lib
-required_ruby_version: !ruby/object:Gem::Requirement 
+required_ruby_version: !ruby/object:Gem::Requirement
   none: false
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      segments: 
-      - 0
-      version: "0"
-required_rubygems_version: !ruby/object:Gem::Requirement 
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
-  requirements: 
-  - - ">="
-    - !ruby/object:Gem::Version 
-      segments: 
-      - 0
-      version: "0"
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
 requirements: []
-
 rubyforge_project: 
-rubygems_version: 1.3.7
+rubygems_version: 1.8.17
 signing_key: 
 specification_version: 3
 summary: A feed fetching and parsing library
-test_files: 
+test_files:
 - spec/benchmarks/feed_benchmarks.rb
 - spec/benchmarks/feedzirra_benchmarks.rb
 - spec/benchmarks/fetching_benchmarks.rb
@@ -265,6 +214,8 @@ test_files:
 - spec/feedzirra/parser/atom_feed_burner_entry_spec.rb
 - spec/feedzirra/parser/atom_feed_burner_spec.rb
 - spec/feedzirra/parser/atom_spec.rb
+- spec/feedzirra/parser/google_docs_atom_entry_spec.rb
+- spec/feedzirra/parser/google_docs_atom_spec.rb
 - spec/feedzirra/parser/itunes_rss_item_spec.rb
 - spec/feedzirra/parser/itunes_rss_owner_spec.rb
 - spec/feedzirra/parser/itunes_rss_spec.rb